cnvd-2025-18930
Vulnerability from cnvd
Title
NVIDIA Triton Inference Server Python后端越界写漏洞
Description
Triton Inference Server是NVIDIA开发的一款高性能推理服务引擎，专为生产环境中的AI模型部署设计，支持多种框架（TensorFlow、PyTorch、ONNX 等），并优化了GPU和CPU的推理性能。 NVIDIA Triton Inference Server Python后端存在越界写漏洞，该漏洞源于内存缓冲区数据越界被写，远程攻击者可利用该漏洞提交特殊的HTTP请求，可以应用程序上下文执行任意代码。
Severity
高
Patch Name
NVIDIA Triton Inference Server Python后端越界写漏洞的补丁
Patch Description
Triton Inference Server是NVIDIA开发的一款高性能推理服务引擎，专为生产环境中的AI模型部署设计，支持多种框架（TensorFlow、PyTorch、ONNX 等），并优化了GPU和CPU的推理性能。 NVIDIA Triton Inference Server Python后端存在越界写漏洞，该漏洞源于内存缓冲区数据越界被写，远程攻击者可利用该漏洞提交特殊的HTTP请求，可以应用程序上下文执行任意代码。目前，供应商发布了安全公告及相关补丁信息，修复了此漏洞。
Formal description

目前厂商已经发布了升级补丁以修复这个安全问题，请到厂商的主页下载: https://github.com/triton-inference-server/server/releases

Reference
https://nvidia.custhelp.com/app/answers/detail/a_id/5687
Impacted products
Name
NVIDIA Triton Inference Server <25.07
Show details on source website

To clipboard 

{
  "cves": {
    "cve": {
      "cveNumber": "CVE-2025-23319",
      "cveUrl": "https://nvd.nist.gov/vuln/detail/CVE-2025-23319"
    }
  },
  "description": "Triton Inference Server\u662fNVIDIA\u5f00\u53d1\u7684\u4e00\u6b3e\u9ad8\u6027\u80fd\u63a8\u7406\u670d\u52a1\u5f15\u64ce\uff0c\u4e13\u4e3a\u751f\u4ea7\u73af\u5883\u4e2d\u7684AI\u6a21\u578b\u90e8\u7f72\u8bbe\u8ba1\uff0c\u652f\u6301\u591a\u79cd\u6846\u67b6\uff08TensorFlow\u3001PyTorch\u3001ONNX \u7b49\uff09\uff0c\u5e76\u4f18\u5316\u4e86GPU\u548cCPU\u7684\u63a8\u7406\u6027\u80fd\u3002\n\nNVIDIA Triton Inference Server Python\u540e\u7aef\u5b58\u5728\u8d8a\u754c\u5199\u6f0f\u6d1e\uff0c\u8be5\u6f0f\u6d1e\u6e90\u4e8e\u5185\u5b58\u7f13\u51b2\u533a\u6570\u636e\u8d8a\u754c\u88ab\u5199\uff0c\u8fdc\u7a0b\u653b\u51fb\u8005\u53ef\u5229\u7528\u8be5\u6f0f\u6d1e\u63d0\u4ea4\u7279\u6b8a\u7684HTTP\u8bf7\u6c42\uff0c\u53ef\u4ee5\u5e94\u7528\u7a0b\u5e8f\u4e0a\u4e0b\u6587\u6267\u884c\u4efb\u610f\u4ee3\u7801\u3002",
  "formalWay": "\u76ee\u524d\u5382\u5546\u5df2\u7ecf\u53d1\u5e03\u4e86\u5347\u7ea7\u8865\u4e01\u4ee5\u4fee\u590d\u8fd9\u4e2a\u5b89\u5168\u95ee\u9898\uff0c\u8bf7\u5230\u5382\u5546\u7684\u4e3b\u9875\u4e0b\u8f7d:\r\nhttps://github.com/triton-inference-server/server/releases",
  "isEvent": "\u901a\u7528\u8f6f\u786c\u4ef6\u6f0f\u6d1e",
  "number": "CNVD-2025-18930",
  "openTime": "2025-08-20",
  "patchDescription": "Triton Inference Server\u662fNVIDIA\u5f00\u53d1\u7684\u4e00\u6b3e\u9ad8\u6027\u80fd\u63a8\u7406\u670d\u52a1\u5f15\u64ce\uff0c\u4e13\u4e3a\u751f\u4ea7\u73af\u5883\u4e2d\u7684AI\u6a21\u578b\u90e8\u7f72\u8bbe\u8ba1\uff0c\u652f\u6301\u591a\u79cd\u6846\u67b6\uff08TensorFlow\u3001PyTorch\u3001ONNX \u7b49\uff09\uff0c\u5e76\u4f18\u5316\u4e86GPU\u548cCPU\u7684\u63a8\u7406\u6027\u80fd\u3002\r\n\r\nNVIDIA Triton Inference Server Python\u540e\u7aef\u5b58\u5728\u8d8a\u754c\u5199\u6f0f\u6d1e\uff0c\u8be5\u6f0f\u6d1e\u6e90\u4e8e\u5185\u5b58\u7f13\u51b2\u533a\u6570\u636e\u8d8a\u754c\u88ab\u5199\uff0c\u8fdc\u7a0b\u653b\u51fb\u8005\u53ef\u5229\u7528\u8be5\u6f0f\u6d1e\u63d0\u4ea4\u7279\u6b8a\u7684HTTP\u8bf7\u6c42\uff0c\u53ef\u4ee5\u5e94\u7528\u7a0b\u5e8f\u4e0a\u4e0b\u6587\u6267\u884c\u4efb\u610f\u4ee3\u7801\u3002\u76ee\u524d\uff0c\u4f9b\u5e94\u5546\u53d1\u5e03\u4e86\u5b89\u5168\u516c\u544a\u53ca\u76f8\u5173\u8865\u4e01\u4fe1\u606f\uff0c\u4fee\u590d\u4e86\u6b64\u6f0f\u6d1e\u3002",
  "patchName": "NVIDIA Triton Inference Server Python\u540e\u7aef\u8d8a\u754c\u5199\u6f0f\u6d1e\u7684\u8865\u4e01",
  "products": {
    "product": "NVIDIA Triton Inference Server \u003c25.07"
  },
  "referenceLink": "https://nvidia.custhelp.com/app/answers/detail/a_id/5687",
  "serverity": "\u9ad8",
  "submitTime": "2025-08-13",
  "title": "NVIDIA Triton Inference Server Python\u540e\u7aef\u8d8a\u754c\u5199\u6f0f\u6d1e"
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or seen somewhere by the user.
  • Confirmed: The vulnerability is confirmed from an analyst perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: This vulnerability was exploited and seen by the user reporting the sighting.
  • Patched: This vulnerability was successfully patched by the user reporting the sighting.
  • Not exploited: This vulnerability was not exploited or seen by the user reporting the sighting.
  • Not confirmed: The user expresses doubt about the veracity of the vulnerability.
  • Not patched: This vulnerability was not successfully patched by the user reporting the sighting.